{"id":"https://openalex.org/W4408901326","doi":"https://doi.org/10.1145/3676641.3716278","title":"Towards End-to-End Optimization of LLM-based Applications with Ayo","display_name":"Towards End-to-End Optimization of LLM-based Applications with Ayo","publication_year":2025,"publication_date":"2025-03-27","ids":{"openalex":"https://openalex.org/W4408901326","doi":"https://doi.org/10.1145/3676641.3716278"},"language":"en","primary_location":{"id":"doi:10.1145/3676641.3716278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3716278","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3676641.3716278","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xin Tan","orcid":"https://orcid.org/0000-0003-3785-9700"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xin Tan","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0003-3785-9700","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079353641","display_name":"Yimin Jiang","orcid":"https://orcid.org/0009-0001-0049-873X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yimin Jiang","raw_affiliation_strings":["Unaffiliated, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0049-873X","affiliations":[{"raw_affiliation_string":"Unaffiliated, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yitao Yang","orcid":"https://orcid.org/0009-0000-1332-7342"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yitao Yang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0009-0000-1332-7342","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022420830","display_name":"Hong Xu","orcid":"https://orcid.org/0000-0002-9359-9571"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hong Xu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":"https://orcid.org/0000-0002-9359-9571","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6484,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96516895,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1302","last_page":"1316"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.8545997142791748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5819642543792725},{"id":"https://openalex.org/keywords/dead-end","display_name":"Dead end","score":0.449358195066452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08532458543777466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0824938416481018}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8545997142791748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5819642543792725},{"id":"https://openalex.org/C2986709869","wikidata":"https://www.wikidata.org/wiki/Q398589","display_name":"Dead end","level":3,"score":0.449358195066452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08532458543777466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0824938416481018},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3676641.3716278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3716278","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3676641.3716278","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3676641.3716278","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2100830825","https://openalex.org/W2252136820","https://openalex.org/W2542459869","https://openalex.org/W2565600385","https://openalex.org/W2780624097","https://openalex.org/W2889787757","https://openalex.org/W2896457183","https://openalex.org/W3027879771","https://openalex.org/W3033527233","https://openalex.org/W4248722156","https://openalex.org/W4281758439","https://openalex.org/W4309591680","https://openalex.org/W4321853806","https://openalex.org/W4361866031","https://openalex.org/W4387321091","https://openalex.org/W4388327470","https://openalex.org/W4389523830","https://openalex.org/W4394998727","https://openalex.org/W4395112660","https://openalex.org/W4399252473","https://openalex.org/W6713134421","https://openalex.org/W6739901393","https://openalex.org/W6851275496"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W3016188207","https://openalex.org/W4400488565","https://openalex.org/W2218833963","https://openalex.org/W2964709658","https://openalex.org/W4240479622","https://openalex.org/W4246369259","https://openalex.org/W1914800454","https://openalex.org/W4237894622"],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)-based":[3],"applications":[4],"consist":[5],"of":[6],"both":[7],"LLM":[8,23],"and":[9,46],"non-LLM":[10],"components,":[11],"each":[12,44],"contributing":[13],"to":[14,21,42],"the":[15],"end-to-end":[16,25],"latency.":[17],"Despite":[18],"great":[19],"efforts":[20],"optimize":[22],"inference,":[24],"workflow":[26],"optimization":[27],"has":[28],"been":[29],"overlooked.":[30],"Existing":[31],"frameworks":[32],"employ":[33],"coarse-grained":[34],"orchestration":[35],"with":[36],"task":[37],"modules,":[38],"which":[39],"confines":[40],"optimizations":[41],"within":[43],"module":[45],"yields":[47],"suboptimal":[48],"scheduling":[49],"decisions.":[50]},"counts_by_year":[{"year":2026,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
